System and method for detecting still objects in images

a still object and image technology, applied in the field of multi-view multi-pose object detection system, can solve the problems of time-consuming, impractical for a real-time system, and difficult task of automatic object detection,

Inactive Publication Date: 2010-12-14
SRI INTERNATIONAL
View PDF6 Cites 65 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Yet, an automatic object detection is a difficult task.
Generating a displacement vector for each pixel (continuous approach), however, is time-consuming and also impractical for a real-time system.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and method for detecting still objects in images
  • System and method for detecting still objects in images
  • System and method for detecting still objects in images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034]Following the two-stage paradigm discussed above, the present invention provides a block diagram of an improved system 200 as illustrated in FIG. 2 for object detection. More specifically, the system 200 provides a computational framework to stably detect still or not moving objects over a wide range of viewpoints. The framework 200 includes providing a sensor input 202 of images which are received by the “focus of attention” mechanism 204 to identify the regions in the image that potentially contain the target objects. These regions are further computed to generate hypothesized objects 206, specifically generating selected regions containing the target object hypothesis with respect to their positions. Thereafter, these selected regions are verified by an extended HOB-based SVM classifier 208 to generate the detected objects 210. The HOG-based SVM classifier 208 is trained via a known bootstrap training process 212 as described by Sung and Poggio in “Example-based learning fo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention provides an improved system and method for object detection with histogram of oriented gradient (HOG) based support vector machine (SVM). Specifically, the system provides a computational framework to stably detect still or not moving objects over a wide range of viewpoints. The framework includes providing a sensor input of images which are received by the “focus of attention” mechanism to identify the regions in the image that potentially contain the target objects. These regions are further computed to generate hypothesized objects, specifically generating selected regions containing the target object hypothesis with respect to their positions. Thereafter, these selected regions are verified by an extended HOG-based SVM classifier to generate the detected objects.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This application claims the benefit of U.S. Provisional Patent Application No. 60 / 832,033 filed Jul. 20, 2006, the entire disclosure of which is incorporated herein by reference.GOVERNMENT RIGHTS IN THIS INVENTION[0002]This invention was made with U.S. government support under contract number NBCHC050078. The U.S. government has certain rights in this invention.FIELD OF THE INVENTION[0003]The invention relates generally to multi-view multi-pose objects detection system. More specifically, the invention relates to a system and method for providing a novel computational framework for detecting still or not moving objects over a range of viewpoints in a static image.BACKGROUND OF THE INVENTION[0004]Automatic object detection and classification is a key enabler for applications in robotics, navigation, surveillance, or automated personal assistance. Yet, an automatic object detection is a difficult task. The main challenge is the amount of va...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(United States)
IPC IPC(8): G06K9/62G06V10/50
CPCG06K9/4642G06V10/50
Inventor HAN, FENGSHAN, YINGCEKANDER, RYANSAWHNEY, HARPREET S.KUMAR, RAKESH
Owner SRI INTERNATIONAL
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap